Dual-Alignment Pre-training for Cross-lingual Sentence Embedding.
Ziheng LiShaohan HuangZihan ZhangZhi-Hong DengQiang LouHaizhen HuangJian JiaoFuru WeiWeiwei DengQi ZhangPublished in: CoRR (2023)
Keyphrases
- cross lingual
- word alignment
- parallel corpus
- machine translation
- cross lingual information retrieval
- language independent
- cross language
- language modeling
- source language
- event extraction
- news articles
- training set
- sentiment classification
- translation model
- natural language
- transfer learning
- document clustering
- data mining
- statistical machine translation
- supervised learning
- pairwise
- parallel corpora
- machine translation system
- sentence level
- distance measure
- co occurrence
- information retrieval systems
- language model
- text classification